Compressed sensing and generative models

Eric Price

doi:10.1117/12.2529939

9 September 2019 Compressed sensing and generative models

Eric Price

Proceedings Volume 11138, Wavelets and Sparsity XVIII; 111380R (2019) https://doi.org/10.1117/12.2529939
Event: SPIE Optical Engineering + Applications, 2019, San Diego, California, United States

Abstract

The goal of compressed sensing is make use of image structure to estimate an image from a small number of linear measurements. The structure is typically represented by sparsity in a well-chosen basis. We describe how to achieve guarantees similar to standard compressed sensing but without employing sparsity at all -instead, we suppose that vectors lie near the range of a generative model G: R^k → Rⁿ. Our main theorem here is that, if G is L-Lipschitz, then roughly O(k log L) random Gaussian measurements suffice; this is O(kd log n) for typical d-layer neural networks. The above result describes how to use a model to recover a signal from noisy data. But if the data is noisy, how can we learn the generative model in the first place? This paper will describe how to incorporate the measurement process in generative adversarial network (GAN) training. Even if the noisy data does not uniquely identify the non-noisy signal, the distribution of noisy data may still uniquely identify the distribution of non-noisy signals. In presenting the above results we summarize and synthesize the work of [BJPD17] and [BPD18]. We then add some observations on the limitations of the approaches.

Citation Download Citation

Eric Price "Compressed sensing and generative models", Proc. SPIE 11138, Wavelets and Sparsity XVIII, 111380R (9 September 2019); https://doi.org/10.1117/12.2529939

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available